English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The Southern Ocean accounts for 40 % of oceanic CO2 uptake, but the\udestimates are bound by large uncertainties due to a paucity in observations.\udGap-filling empirical methods have been used to good effect to approximate\udpCO2 from satellite observable variables in other parts of the ocean,\udbut many of these methods are not in agreement in the Southern Ocean. In this\udstudy we propose two additional methods that perform well in the Southern\udOcean: support vector regression (SVR) and random forest regression (RFR).\udThe methods are used to estimate ΔpCO2 in the Southern Ocean based\udon SOCAT v3, achieving similar trends to the SOM-FFN method by\udLandschützer et al. (2014). Results show that the SOM-FFN and RFR approaches\udhave RMSEs of similar magnitude (14.84 and 16.45 µatm, where\ud1 atm  =  101 325 Pa) where the SVR method has a larger RMSE\ud(24.40 µatm). However, the larger errors for SVR and RFR are, in\udpart, due to an increase in coastal observations from SOCAT v2 to v3, where\udthe SOM-FFN method used v2 data. The success of both SOM-FFN and RFR depends\udon the ability to adapt to different modes of variability. The SOM-FFN\udachieves this by having independent regression models for each cluster, while\udthis flexibility is intrinsic to the RFR method. Analyses of the estimates\udshows that the SVR and RFR's respective sensitivity and robustness to\udoutliers define the outcome significantly. Further analyses on the methods\udwere performed by using a synthetic dataset to assess the following: which\udmethod (RFR or SVR) has the best performance? What is the effect of using\udtime, latitude and longitude as proxy variables on ΔpCO2? What is\udthe impact of the sampling bias in the SOCAT v3 dataset on the estimates? We\udfind that while RFR is indeed better than SVR, the ensemble of the two\udmethods outperforms either one, due to complementary strengths and weaknesses\udof the methods. Results also show that for the RFR and SVR implementations,\udit is better to include coordinates as proxy variables as RMSE scores are\udlowered and the phasing of the seasonal cycle is more accurate. Lastly, we\udshow that there is only a weak bias due to undersampling. The synthetic data\udprovide a useful framework to test methods in regions of sparse data coverage\udand show potential as a useful tool to evaluate methods in future studies

Empirical methods for the estimation of Southern Ocean CO&lt;sub&gt;2&lt;/sub&gt;: support vector and random forest regression

Empirical methods for the estimation of Southern Ocean CO<sub>2</sub>: support vector and random forest regression